NYC
skills/letta-ai/skills/yelp-search/Gen Agent Trust Hub

yelp-search

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [Prompt Injection] (LOW): The scripts/get_reviews.py script interpolates user-supplied business names and locations directly into a natural language task for an LLM-driven browser agent.
  • Ingestion points: CLI arguments 'business' and 'location' in get_reviews.py.
  • Boundary markers: None; user data is not delimited within the prompt template.
  • Capability inventory: Browser interaction and data extraction via browser-use.
  • Sanitization: Inputs are used raw without validation or escaping.
  • [External Downloads] (LOW): The skill setup instructions require downloading browser binaries using Playwright (playwright install chromium), which is a standard procedure for browser automation tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:58 PM